Borrowing it
Nothing to install: this file belongs to sophonfinance-wq/finance-automation-portfolio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sophonfinance-wq/finance-automation-portfolio/main/.claude/skills/recon/SKILL.mdgit clone --depth 1 https://github.com/sophonfinance-wq/finance-automation-portfolioWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/recon)<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/recon"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/recon/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/sophonfinance-wq/finance-automation-portfolio/recon"><img src="https://agentmods.dev/badge/skills/sophonfinance-wq/finance-automation-portfolio/recon.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00044 | $0.00358 |
| Opus 5 | $0.00022 | $0.00179 |
| Sonnet 5 | $0.00009 | $0.00072 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
recon scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Cash & Debt Reconciliation Engine
Package recon_engine in cash-reconciliation/. Seed 20260331, materiality $50, always exit 0 for the base CLI (flags are an expected outcome, not a failure).
Commands (run from cash-reconciliation/)
python -m recon_engine # reconcile; writes evidence-log.md + xlsx
python -m recon_engine --threshold 25 --no-xlsx
python -m recon_engine.loop --demo # ASSURANCE LOOP: restore drifted package to source
python -m pytest -q # 7,511 tests
Loop verdicts (recon_engine/loop.py)
PASS (0) / FLAG (0, material corrections booked for review) / FAIL (1, unconverged).
Key property: fidelity, not zeroing — the scenario's genuine reconciling items (deposit-in-transit, keying error) are part of the baseline and survive the loop. Baseline = reconcile(generate_dataset(seed)), not "all clean".
Key files
recon_engine/engine.py— classify clean/timing/flag by account number; lender 3-part totalrecon_engine/generate.py— frozen dataclasses; usedataclasses.replaceto inject driftrecon_engine/loop.py— per-account resync (GL row, statements, dormant marker)
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 25 lines · 44 tokens per session scan A 1aaeb82d3d6d
recon is a skill published in the GitHub repository sophonfinance-wq/finance-automation-portfolio (11 stars, last pushed 16d ago), licensed MIT. It adds 44 tokens to every session and 358 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Invoice Automation
Automate invoice generation, sending, tracking, and payment reconciliation across accounting platforms.
correction-memory
A local memory system that stores tax-accountant corrections to transaction classifications. It matches future transactions to earlier vendor or description patterns.
nightly-batch
Batch-process all client companies overnight. Fetches unprocessed transactions from freee API, runs the full classification pipeline, and generates a summary for morning review.
tax-classifier
A system for assigning Japanese business transactions to accounting categories, called 勘定科目, and consumption-tax treatments. It checks exclusions, past corrections, keywords, and then uses AI when needed.
csv-importer
A tool for importing transaction CSV files—spreadsheet files separated by commas—from Japanese accounting software and classifying every imported row.
bank-reconciliation
Match book entries against bank or credit card statements to find discrepancies, missing transactions, and duplicates. Uses exact, near, and batch matching with balance verification. Trigger on "reconcile bank statement", "match transactions", "bank balance doesn't match", "close the books".